The Agent Skills Directory

[PROMPT_INJECTION]: The skill definition creates a vulnerability surface for indirect prompt injection by enabling the agent to ingest and process data from external files and JSON strings.
Ingestion points: The functions scriptableobject_import_json and scriptableobject_get read data from file paths or strings that may be controlled by an external actor.
Boundary markers: There are no instructions or delimiters defined to help the agent distinguish between data and potential commands within the processed JSON.
Capability inventory: The skill allows for the creation, modification, and deletion of files on the system (scriptableobject_delete, scriptableobject_create, scriptableobject_export_json), which could be abused if an injection is successful.
Sanitization: The skill lacks specified validation or sanitization for the inputs provided to the asset management tools.

unity-scriptableobject